A Steel Plate Rolling Mill (SPM) is a milling machine that uses rollers to press hot slab inputs to produce ferrous or non-ferrous metal plates. To produce high-quality steel plates, it is important to precisely detect and sense values of manufacturing factors including plate thickness and roll force in each rolling pass. For example, the estimation or prediction of the in-process thickness is utilized to select the control values (e.g., roll gap) in the next pass of rolling. However, adverse manufacturing conditions can interfere with accurate detection for such manufacturing factors. Although the state-of-the-art gamma-ray camera can be used for measuring the thickness, the outputs from it are influenced by adverse manufacturing conditions such as the high temperature of plates, followed by the evaporation of lubricant water. Thus, it is inevitable that there is noise in the thickness estimation. Furthermore, installing such thickness measurements for each passing step is costly. The precision of the thickness estimation, therefore, significantly affects the cost and quality of the final product. In this paper, we present machine learning (ML) technologies and models that can be used to predict the in-process thickness in the SPM operation, so that the measurement cost for the inprocess thickness can be significantly reduced and high-quality steel plate production can be possible. To do so, we investigate most-known technologies in this application. In particular, Data Clustering based Machine Learning (DC-ML), combining clustering algorithms and supervised learning algorithms, is introduced. To evaluate DC-ML, two experiments are conducted and show that DC-ML is well suited to the prediction problems in the SPM operation. In addition, the source code of DC-ML is provided for the future study of machine learning researchers. INDEX TERMS Intelligent manufacturing systems, machine learning, regression analysis, steel industry, thickness control.
Projects on steel‐making plant follow the stages of steel‐making plant system life cycle. In each life cycle stage, there are exit criteria to be fulfilled before a project can continue to the next stage. Among the exit criteria, we focus on one of the technical exit criteria, that is, the technology maturity. Technology maturity is measured using technical readiness level (TRL) and TRL concept has been largely adopted by numerous organizations and industry. However, the assignment of a certain TRL as one of the exit criteria of life cycle stages are not well adapted. In other words, TRL is not considered as a critical exit criteria of a system life cycle stages. In this paper, we would like to propose that the TRL should be one of the exit criteria of each life cycle stage. In this research, we propose a steel‐making plant system life cycle, define the technical readiness level for a steel‐making plant, and assign a target TRL for each life cycle stage as an exit criteria of that stage. The benefits of target TRL assignment to the life cycle stages are as follows: (1) the technical risk of developing/inserting a technology can be controlled on each life cycle stage, (2) the cost incurred if the technology to be developed/inserted is failed can be analyzed in each life cycle stage, and (3) as a standardization effort of technology readiness at each industrial plant life cycle stage. By directly assigning target TRL for each life cycle stages, we look forward to a more coordinated (in terms of exit criteria) and highly effective (in terms of technical risks identification and eventually project failure prevention) technology development and assessment processes.
Abstract. Lock housing assembly is a vehicle component which is designed and manufactured by a 2nd tier supplier of a car maker. This paper showed a middle-out systems engineering approach for a gray box item development. In the case of gray box item development, the communication between a car maker and suppliers is a key success factor to overcome unclear and unbalanced design responsibility from the viewpoint of supplier. To show the middle-out systems engineering process, this paper addressed the development of a magnesium lock housing assembly. This project used some methodologies such as Quality Function Deployment (hereafter QFD) and functional flow diagram etc. to enhance communication capabilities. The customer requirements were developed with QFD while functional flow diagram was used to derive quality control parameters.
The concept of Smart Factory, a new paradigm in manufacturing industry, has emerged and is expanding exponentially. This shift is apparent in new IT such as Cyber Physical Systems (CPS), Artificial Intelligence (AI), and Cloud Computing. Varieties of Smart Factory architecture applying these technologies are already widespread. However, most of the widespread architecture only define manufacturing levels from Level 0 (Physical Processing) to Level 4 (Business Logistics Systems) and specify services that are provided between them. These technical specifications do not guide the development processes and do not provide the architecture to implement Smart Factory infrastructure within existing factory. In this paper, we propose Smart Service System‐based Smart Factory (4SF) architecture that can be utilized without major changes to existing systems by using “add‐on” concepts of Smart Factory. Furthermore, we applied Systems Engineering process to enable system design based on requirements in manufacturing industry using an operational, system and technology model. Finally, these concepts were applied to a steel plate plant to show practical potential of Smart Service System‐based Smart Factory.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.